A novel transfer learning model for traditional herbal medicine prescription generation from unstructured resources and knowledge

作者：

Highlights：

• A transfer learning method to learn the interactions between herbal medicines and clinical symptoms from unstructured text resources and a few of labeled samples.

• A universal deep learning method to deal with medical text resources for clinical tasks.

• The first case study and application of deep learning method in herbal medicine prescription generation from very limited clinical records.

摘要

•A transfer learning method to learn the interactions between herbal medicines and clinical symptoms from unstructured text resources and a few of labeled samples.•A universal deep learning method to deal with medical text resources for clinical tasks.•The first case study and application of deep learning method in herbal medicine prescription generation from very limited clinical records.

论文关键词：Artificial intelligence,Traditional herbal medicine,Transfer learning,Natural language understanding,Intelligent medicine

论文评审过程：Received 19 February 2021, Revised 30 November 2021, Accepted 17 December 2021, Available online 31 December 2021, Version of Record 7 January 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102232